INDEX

Explanations

phrases indicating repetition or similarity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

egis

-0.15

)((((

-0.15

pery

-0.15

anse

-0.15

ķãĤĵ

-0.15

ãĤ·ãĤ§

-0.14

agli

-0.14

aoke

-0.14

mine

-0.14

chy

-0.14

POSITIVE LOGITS

orex

0.17

cket

0.17

à¥Īà¤²

0.15

 Butterfly

0.15

angelo

0.15

Typed

0.14

estre

0.14

ushima

0.14

 inexperienced

0.14

Activations Density 0.146%

phrases indicating repetition or similarity

No Comments

No Known Activations